Agricultural Price Forecasting using Decomposition-based Hybrid Model

DOI: 10.18805/BKAP435    | Article Id: BKAP435 | Page : 18-22
Citation :- Agricultural Price Forecasting using Decomposition-based Hybrid Model.Bhartiya Krishi Anusandhan Patrika.2022.(37):18-22
Kapil Choudhary, Girish Kumar Jha, Rajeev Ranjan Kumar, Ronit Jaiswal rrk.uasd@gmail.com
Address : ICAR-Indian Agricultural Statistics Research Institute, New Delhi-110 012, India.
Submitted Date : 18-01-2022
Accepted Date : 11-05-2022


Agricultural price information needs for decision-making at all levels are increasing due to globalization and market integration. Due to its great reliance on biological processes, agricultural price forecasting is one of the most difficult fields of time series analysis. In this paper, a neural network model based on empirical mode decomposition is used to forecast potato prices. The monthly wholesale price series of potato from Chennai market was decomposed into five independent intrinsic modes (IMFs) and one residual with various frequencies. Then, to forecast these IMFs and residual components independently, an artificial neural network with a single hidden layer was built. Finally, the ensemble output for the original price series is formed by aggregating the forecast outcomes of all IMFs, including residuals. In terms of root mean square error and directional prediction statistics, empirical data show that the suggested ensemble model outperforms a single model.


​Artificial neural network Empirical mode decomposition Intrinsic mode function Price forecasting


  1. Banerjee, R., Das, P., Ahmad, T. and Kumar, M. (2021). Modeling and forecasting of agricultural commodity production under changing climatic condition: A review. Bhartiya Krishi Anusandhan Patrika. 36(4): 273-279.
  2. Box, G.E.P. and Jenkins, G.M. (1970). Time Series Analysis: Forecasting and Control. Holden-Day, San Francisco, CA.
  3. Clements, M.P. and Smith, J. (1997). The performance of alternative forecasting methods for SETAR models. International Journal of Forecasting.  13(4): 463-475.
  4. Choudhary, K., Jha, G.K. and Kumar, R.R. (2019). Delhi Potato price analysis using ensemble empirical mode decomposition. Bharatiya Krishi Anusandhan Patrika. 34(1): 33-37.
  5. Choudhury, K., Jha, G.K., Kumar, R.R. and Mishra, D.C. (2019). Agricultural commodity price analysis using ensemble empirical mode decomposition: A case study of daily potato price series. Indian Journal of Agricultural Sciences. 89(5): 882-886.
  6. Darbellay, G.A. and Slama, M. (2000). Forecasting the short-term demand for electricity: Do neural networks stand a better chance? International Journal of Forecasting. 16(1): 71-83.
  7. Huang, N.E., Shen, Z., Long, S.R., Wu, M. C., Shih, H.H., Zheng, Q. and Liu, H.H. (1998). The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. In Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. 454: 903-995.
  8. Jha, Girish, K. and Sinha, K. (2013). Agricultural price forecasting using neural network model: An innovative information delivery system. Agricultural Economics Research Review. 26(2): 229-239. 
  9. Nelson, M., Hill, T., Remus, W. and O’Connor, M. (1999). Time series forecasting using neural networks: Should the data be deseasonalized first?. Journal of Forecasting. 18(5): 359-367.
  10. Kumar, R.R., Jha, G.K., Choudhary, K. and Budhlakoti, N. (2019). Examining integration between Agra and Delhi potato markets. Bhartiya Krishi Anusandhan Patrika. 34(1): 62-64.
  11. Zhang, X., Lai, K.K. and Wang, S.Y. (2008). A new approach for crude oil price analysis based on empirical mode decomposition. Energy Economics. 30(3):  905-918.
  12. Zhang, J.L., Zhang, Y.J. and Zhang, L. (2015). A novel hybrid method for crude oil price forecasting.  Energy  Economics. 49: 649-659.
  13. Zhu, B. (2012). A novel multiscale ensemble carbon price prediction model integrating empirical mode decomposition, genetic algorithm and artificial neural network. Energies. 5(2): 355-370.

Global Footprints